CN106210517A - The processing method of a kind of view data, device and mobile terminal - Google Patents
The processing method of a kind of view data, device and mobile terminal Download PDFInfo
- Publication number
- CN106210517A CN106210517A CN201610530720.8A CN201610530720A CN106210517A CN 106210517 A CN106210517 A CN 106210517A CN 201610530720 A CN201610530720 A CN 201610530720A CN 106210517 A CN106210517 A CN 106210517A
- Authority
- CN
- China
- Prior art keywords
- colour
- image data
- skin
- color value
- view data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
Embodiments providing the processing method of a kind of view data, device and mobile terminal, the method includes: obtain the raw image data of camera collection;The first volumetric image data is identified in described raw image data;Obtain the Image Processing parameter arranged when processing for the second human body image data;According to described Image Processing parameter, described the first volumetric image data is processed, it is thus achieved that destination image data.The embodiment of the present invention allows to the experience by using for reference other users, quickly arrange Image Processing parameter to process, greatly reduce the technical threshold of image procossing, in the case of user is unfamiliar to the technology of these image procossing, it is also ensured that arrange relatively reasonable Image Processing parameter, the quality of view data after raising process.
Description
Technical field
The present invention relates to the technical field of communication, particularly relate to the processing method of a kind of view data, a kind of picture number
According to processing means and a kind of mobile terminal.
Background technology
Along with the fast development of mobile communication technology, the such as mobile terminal such as mobile phone, panel computer have been widely used in
Practise, entertain, the aspect such as work, daily life plays the most important role.
It is commonly configured with photographic head in the terminal, and owing to mobile terminal is relative to photographing unit, has easy to carry
Etc. characteristic, therefore, many user habits use mobile terminal to take pictures.
Such as autodyning, under the sight such as group photo, people can be taken pictures by user, various owing to can carry out during taking pictures
Image procossing, the debugging cycle of these image procossing is long, and the technical threshold of these image procossing is higher, user to these images
Process technology unfamiliar in the case of, it is easy to arrange mistake Image Processing parameter, cause process after view data
Degradation.
Such as, when the colour of skin is carried out image procossing, being controlled by image procossing, stability in the large is poor, causes the colour of skin
Under circumstances, show different.
Summary of the invention
In view of the above problems, it is proposed that the present invention in case provide one overcome the problems referred to above or at least in part solve on
State processing method and the processing means of corresponding a kind of view data, a kind of mobile terminal of a kind of view data of problem.
First aspect, provides the processing method of a kind of view data in the embodiment of the present invention, including:
Obtain the raw image data of camera collection;
The first volumetric image data is identified in described raw image data;
Obtain the Image Processing parameter arranged when processing for the second human body image data;
According to described Image Processing parameter, described the first volumetric image data is processed, it is thus achieved that destination image data.
Second aspect, embodiments provides the processing means of a kind of view data, including:
Raw image data acquisition module, for obtaining the raw image data of camera collection;
Human body image data identification module, for identifying the first volumetric image data in described raw image data;
Image Processing parameter acquisition module, the image arranged when processing for the second human body image data for obtaining
Processing parameter;
Human body image data processing module, for entering described the first volumetric image data according to described Image Processing parameter
Row processes, it is thus achieved that destination image data.
The third aspect, embodiments provides a kind of mobile terminal, and this mobile terminal has and realizes above-mentioned first party
The function processing behavior of view data in face.Described function can be realized by hardware, it is also possible to performed corresponding by hardware
Software realize.Described hardware or software include one or more module corresponding with above-mentioned functions.
In a possible design, the structure of mobile terminal includes that processor and memorizer, described memorizer are used for
Storage supports that R-T unit performs the program of said method, and described processor is configurable for performing to store in described memorizer
Program.Described mobile terminal can also include communication interface, for mobile terminal and other equipment or communication.
Wherein, described memorizer is for storing the instruction of the raw image data obtaining camera collection, described original
View data identifies the instruction of the first volumetric image data, obtains and arrange when processing for the second human body image data
The instruction of Image Processing parameter, according to described Image Processing parameter, described the first volumetric image data is processed, it is thus achieved that
Destination image data instructs;
Described processor is used for:
According to the instruction of the raw image data of described acquisition camera collection, obtain the original image number of camera collection
According to;
In described raw image data, the instruction of the first volumetric image data is identified, at described original image according to described
Data identify the first volumetric image data;
The instruction of the Image Processing parameter arranged when processing for the second human body image data according to described acquisition, obtains
Take the Image Processing parameter arranged when processing for the second human body image data;
Described the first volumetric image data is processed according to described Image Processing parameter according to described, it is thus achieved that target figure
As the instruction of data, according to described Image Processing parameter, described the first volumetric image data is processed, it is thus achieved that target image
Data.
The scheme that the present invention provides, user can use mobile terminal, obtains the original graph that photographic head gathers when preview
As data, therefrom identify the first volumetric image data, according to the image arranged when processing for the second human body image data
Processing parameter, carries out image procossing to the first volumetric image data, it is thus achieved that destination image data so that can be by using for reference other
The experience of user, quickly arranges Image Processing parameter and processes, greatly reduce the technical threshold of image procossing, user couple
In the case of the technology of these image procossing is unfamiliar, it is also ensured that relatively reasonable Image Processing parameter is set, at raising
The quality of view data after reason.
The scheme that the present invention provides, user can use mobile terminal, according to target colour of skin color value to colour of skin picture number
According to being normalized so that the colour of skin of input can tend to, be even up to the target colour of skin, solves the colour of skin by image procossing
Control, stability in the large is poor, causes the colour of skin under circumstances, shows different problem, the colour of skin that output is stable, consistent,
Meanwhile, the debugging cycle of image procossing is shortened.
The aspects of the invention or other aspects be meeting more straightforward in the following description.
Accompanying drawing explanation
By reading the detailed description of hereafter preferred implementation, various other advantage and benefit common for this area
Technical staff will be clear from understanding.Accompanying drawing is only used for illustrating the purpose of preferred implementation, and is not considered as the present invention
Restriction.And in whole accompanying drawing, it is denoted by the same reference numerals identical parts.In the accompanying drawings:
Fig. 1 shows the steps flow chart of the processing method embodiment of a kind of view data
Figure;
Fig. 2 shows the step stream of the processing method embodiment of another kind of according to an embodiment of the invention view data
Cheng Tu;
Fig. 3 shows the structural frames of the processing means embodiment of a kind of view data
Figure;
Fig. 4 shows the structural frames of the processing means embodiment of another kind of according to an embodiment of the invention view data
Figure;And
Fig. 5 shows the block diagram of the part-structure of mobile phone relevant to mobile terminal according to an embodiment of the invention.
Detailed description of the invention
It is more fully described the exemplary embodiment of the disclosure below with reference to accompanying drawings.Although accompanying drawing shows the disclosure
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure and should be by embodiments set forth here
Limited.On the contrary, it is provided that these embodiments are able to be best understood from the disclosure, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
With reference to Fig. 1, it is shown that the step of the processing method embodiment of a kind of view data
Rapid flow chart, specifically may include steps of:
Step 101, obtains the raw image data of camera collection.
In implementing, the embodiment of the present invention can be applied in the terminal, such as, and mobile phone, panel computer, individual
Digital assistants, wearable device (such as glasses, wrist-watch etc.) etc..
The operating system of these mobile terminals can include Android (Android), IOS, Windows Phone, Windows
Etc..
In embodiments of the present invention, photographic head camera can be configured in the terminal.
These photographic head can be only fitted to the front portion (also known as front-facing camera) of mobile terminal, it is also possible to is arranged in mobile whole
End back (also known as post-positioned pick-up head), additionally, the quantity of this photographic head can be single, can also be two or two with
On, such as dual camera, etc., this is not any limitation as by the embodiment of the present invention.
In one example, photographic head can include camera lens Lens, pedestal Holder, infrared filter IR, image sensing
The parts such as processor Sensor, circuit board.
Wherein, image sensing processor Sensor is a kind of semiconductor chip, and its surface includes hundreds of thousands to millions of
The photodiode not waited, when photodiode receives light irradiation, can produce electric charge.
Image sensing processor Sensor can convert light into the signal of telecommunication, then is turned by internal DA (digital-to-analogue conversion)
It is changed to digital signal, the imaging plane that plane is view data at image sensing processor Sensor place.
In actual applications, the optical imagery that scenery (SCENE) is generated by the camera lens Lens of photographic head projects image
On sensing processor Sensor surface, then turn to the signal of telecommunication, after A/D (analog digital conversion) changes, become digital picture letter
Number, by data image signal is compressed and is converted into specific image literary composition by digital signal processing chip DSP or code database
Part form, is located by the processor (Central Processing Unit, CPU) of data bus transmission to mobile terminal
Reason, then can show at the screen of mobile terminal.
Step 102, identifies the first volumetric image data in described raw image data.
So-called human body image data, refers to characterize the view data of people in raw image data.
In the sights such as auto heterodyne, it is usually and a people is taken pictures, therefore, raw image data can identify one
Individual human body image data;In the sights such as group photo, it is usually and many individuals are taken pictures, therefore, can in raw image data
To identify multiple human body image datas.
In implementing, human body image data can be detected by one or more following modes:
1, based on template or the detection method of profile
Detection method based on template or profile mainly uses the method for template matching and template classification to detect human figure
As data.
In one example, the contour feature of human body can be applied during various level template matching to select to wait
The target of choosing, the shape appearance typically exhibited by human body is as human body target template, according to the shape matching method of range conversion
Mate from coarse to fine.Then, RBF is re-used to verify the target of candidate.
2, detection method based on movable information
Detection method based on movable information is to utilize the periodicity of human motion to carry out the people in inspection image data, typically
It is applicable to the pedestrian of detection motion.
In one example, when utilizing people to walk, leg is periodic motion feature, identifies people from image sequence,
First view data it is divided into sub-image data and pixel is clustered, in continuous print view data, then mating the class of correspondence
And follow the tracks of all kinds of, the time based on class row shape feature changes, and estimates that carrying out initial option may belong to quick multinomial grader
The class of people's leg, the class that extraction belongs to leg finally by neutral net is trained, thus judges whether people.
3, detection method based on sliding window
The detection method based on sliding window detection window slip scan in view data by fixed size, these
Window is classified device and has been categorized as people and nobody two classes.
In one example, the detection method of sliding window can be divided into two stages, and first stage is the training stage,
Second stage is detection-phase.
In the training stage, initially setting up training sample, including positive sample and negative sample, positive sample is exactly the figure including human body
As region, negative sample is exactly the image-region not including human body.Then from positive sample and negative sample, extract feature, this feature one
As represent with the form of characteristic vector.Finally training grader, this grader is for by the characteristic vector of positive sample and negative sample
Characteristic vector make a distinction.
At detection-phase, owing in view data, human's judgment size is indefinite, and being typically of size of of sliding window
Certain, in order to the little people of yardstick and the big people of yardstick can be detected, the figure of band inspection image data can be set up
As pyramid, use the sliding window of fixed size to slide in each level of pyramid, often slide into a position just by this
The characteristics of image input grader extracted in individual window is classified.Grader exports whether this window comprises the letter of people
Breath.When all positions and level the most the most scanned by sliding window after, the windows detecting that in each level, position is close arrives
People is likely to same person, in order to determine the position of final human body, carries out window fusion and adjacent window is merged into one
Window.
4, based on parts or the detection method of local shape
Based on be not or local shape method rely on detection human body not for or local shape, combine this most again
A little features limit the position determining final human body according to the geometry of anthropometric dummy.
Certainly, above-mentioned human detection is intended only as example, when implementing the embodiment of the present invention, can set according to practical situation
Putting other human detection, this is not any limitation as by the embodiment of the present invention.It addition, in addition to above-mentioned human detection, art technology
Personnel can also use other human detection according to actual needs, and this is not any limitation as by the embodiment of the present invention.
Step 103, obtains the Image Processing parameter arranged when processing for the second human body image data.
In embodiments of the present invention, if people is taken pictures by other users, it is thus achieved that view data, if in this view data
Detection somatic data, and human body image data has been carried out image procossing, then can record the Image Processing parameter now arranged.
In an application example, after certain star or the intelligent that takes pictures autodyne, photo is carried out image procossing, then can protect
Deposit this star or the Image Processing parameter of the intelligent that takes pictures setting, and be shared with other users.
In implementing, Image Processing parameter can include target colour of skin color value, face size parameter, body size
The smooth degree of parameter, skin, blood-shot eye illness parameter, black eye parameter, eyes size parameter etc..
Wherein, target colour of skin color value may be used for being adjusted the colour of skin, and face size parameter may be used for regulating people
The size of face, body size parameter may be used for regulating the size of health, the smooth degree of skin may be used for adjusting the flat of skin
Whole degree, may be used for eliminating comedo, nevus etc., and blood-shot eye illness parameter may be used for eliminating blood-shot eye illness, and black eye parameter may be used for disappearing
Except black eye, eyes size parameter may be used for regulating the size of eyes.
It should be noted that these Image Processing parameter are typically what different user was arranged;Additionally, these image procossing ginseng
Number can store in the server, it is also possible to is stored in mobile terminal local, the most in embodiments of the present invention, in the terminal
The Image Processing parameter that inquiry is arranged when processing for the second human body image data, it is also possible to server request ask for
The Image Processing parameter arranged when second human body image data processes, this is not any limitation as by the embodiment of the present invention.
Step 104, processes described the first volumetric image data according to described Image Processing parameter, it is thus achieved that target figure
As data.
If inquiring Image Processing parameter, then the first volumetric image data of these Image Processing parameter can be directly applied to enter
Row image procossing, it is thus achieved that destination image data.
The scheme that the present invention provides, user can use mobile terminal, obtains the original graph that photographic head gathers when preview
As data, therefrom identify the first volumetric image data, according to the image arranged when processing for the second human body image data
Processing parameter, carries out image procossing to the first volumetric image data, it is thus achieved that destination image data so that can be by using for reference other
The experience of user, quickly arranges Image Processing parameter and processes, greatly reduce the technical threshold of image procossing, user couple
In the case of the technology of these image procossing is unfamiliar, it is also ensured that relatively reasonable Image Processing parameter is set, at raising
The quality of view data after reason.
In one embodiment of the invention, step 104 can include following sub-step:
Sub-step S11, identifies colour of skin view data from described the first volumetric image data;
In embodiments of the present invention, colour of skin picture number can be identified by Face Detection from the first volumetric image data
According to.
So-called Face Detection, is to choose the process corresponding to human skin pixels in view data.
According to either with or without relating to imaging process, Face Detection can mark off the following two kinds type:
1, Face Detection based on statistics
The key step of Face Detection based on statistics includes color notation conversion space and skin color modeling.
Color space is selected inherently to select the most basic character representation of Face Detection.Skin color modeling is to know about the colour of skin
The computer representation known, generally sets up complexion model by training sample set and carries out Face Detection, can be by according to different application
Skin color modeling is divided into static and dynamic two classes.
Wherein, for color space, the colour of skin is quite concentrated in the distribution of color space, but can by illumination with ethnic group very
Big impact, is affected by intensity of illumination to reduce the colour of skin, and color space is generally converted into brightness and colourity classification certain from RGB
Individual color space, such as YCbCr or HSV, then abandon brightness.
For static skin color modeling, the sides such as skin color range, Gaussian density function estimation and statistics with histogram can be passed through
Formula sets up complexion model, the most corresponding thresholding of this three, parametrization and the method for imparametrization.
For dynamic skin color modeling, can by complexion model parameter is adjusted to adapt to certain width still image, or,
For sequence image, adapt to the image-forming condition mode such as over time and set up complexion model.
2, Face Detection based on physics
Under complicated lighting condition, in such as image, the colour of skin is in specular or shadow region, in order to from imaging mechanism on gram
Take illumination and image paid no attention to impact, when Face Detection, it is considered to the interaction of light and skin, it is considered to skin POP is special
Property, this Face Detection technology referred to as Face Detection based on physics considering electromagnetic radiation and the mutual physical action of skin.
In a kind of Face Detection mode based on physics, colour of skin inspection can be carried out by the physical model of skin reflex
Surveying, such as, dichromatic reflection model can simulate opaque non-uniform dielectric thing according to the reflection characteristic of non-uniform dielectric
Body reflection process, to carry out Face Detection.
In an example of the embodiment of the present invention, owing to taking pictures people, especially autodyning, face is composition
One of pith, therefore, it can carry out Face datection in raw image data, it is thus achieved that face image data, at this face
View data identifies colour of skin view data.
So-called Face datection, can refer to calibrate the positions and dimensions of face from view data.
In Android, it is provided that a method directly carrying out face detection on bitmap, the two API
(Application Programming Interface, application programming interface) is respectively
Android.media.FaceDetector and android.media.FaceDetector.Face.
Specifically, extend base class ImageView, become MyImageView, and carry out the bitmap comprising face detected
File is usually 565 forms, to ensure that API normally works.
The face being detected needs a confidence measure (confidence measure), and this measure is defined on
android.media.FaceDetector.Face.CONFIDENCE_THRESHOLD。
Wherein, FaceDetector object-instantiated can be called findFaces by setFace () simultaneously, and result is deposited
In faces, MyImageView is transferred at the midpoint of face.
It follows that add setDisplayPoints () method in MyImageView, it is used at the face being detected
Upper labelling renders.
And API returns the information that other are useful, such as, such as eyesDistance, pose can be returned simultaneously, and
Confidence, then can position the center of eyes by eyesDistance.
Certainly, above-mentioned Face Detection is intended only as example, when implementing the embodiment of the present invention, can set according to practical situation
Putting other Face Detection, this is not any limitation as by the embodiment of the present invention.It addition, in addition to above-mentioned Face Detection, art technology
Personnel can also use other Face Detection according to actual needs, and this is not any limitation as by the embodiment of the present invention.
Sub-step S12, is normalized described colour of skin view data according to described target colour of skin color value.
In implementing, if colour of skin view data being detected in human body image data, then can be according to the target colour of skin
This colour of skin view data is normalized by color value.
As a example by RGB color, in target colour of skin color value, R (red) value is generally higher than G (green) value, and G (green) value is general
More than B (blue) value, such as (215,177,141), (249,217,204), (253,227,204) etc..
Be normalized with colour of skin view data by target colour of skin color value, can allow input colour of skin picture number
According to the colour of skin tend to, even up to target colour of skin color value, the colour of skin that output is stable, consistent.
In actual applications, Eigen Skin color image can be selected in colour of skin view data by certain selection rule
Data, are normalized Eigen Skin color view data according to target colour of skin color value.
For example, it is possible to select Eigen Skin color view data according to brightness and/or exposure, screen out some brightness irregularities,
The colour of skin view data of overexposure, retains brightness uniformity, does not has the colour of skin view data of overexposure.
Specifically, brightness and/or the exposure of colour of skin view data can be added up by modes such as statistics with histogram.
From colour of skin view data, choose brightness be less than, in default brightness section and/or exposure, the threshold exposure preset
View data, as Eigen Skin color view data.
Certainly, it is normalized except selected part colour of skin view data, it is also possible to whole colour of skin view data
Being normalized, this is not any limitation as by the embodiment of the present invention.
In one embodiment of the invention, sub-step S12 can include following sub-step:
Sub-step S121, adds up the original colour of skin color value in described colour of skin view data;
In implementing, the pixel color value of each pixel in colour of skin view data can be obtained, such as rgb value, calculate
The meansigma methods of pixel color value, as original colour of skin color value.
Sub-step S122, uses described original colour of skin color value to calculate normalization coefficient with described target colour of skin color value;
In implementing, normalization coefficient can be calculated based on calculating target colour of skin color value, adjust original skin with this
Color color value.
In an example of the embodiment of the present invention, sub-step S122 can include following sub-step:
Sub-step S1221, calculates the ratio between described target colour of skin color value and original colour of skin color value, it is thus achieved that color
Adjustment ratio;
As a example by RGB color, it is assumed that target colour of skin color value is (Rsample, Gsample, Bsample), photographic head inputs
The original colour of skin color value of colour of skin view data be (Rinput, Ginput, Binput), then, it is (R that color adjusts ratioratio,
Gratio, Bratio):
Rratio=Rsample/Rinput
Gratio=Gsample/Ginput
Bratio=Bsample/Binput
Sub-step S1222, is multiplied by described adjustment ratio by the pixel color value of each pixel in described colour of skin view data,
Obtain pixel color value set.
Sub-step S1223, chooses object pixel color value from described pixel color value set.
In implementing, can be from pixel color value set, the pixel color value that selected value is maximum, as target picture
Element color value.
Certainly, in addition to the pixel color value of selected value maximum, it is also possible to choose other pixel color value as target
Pixel color value, this is not any limitation as by the embodiment of the present invention.
As a example by RGB color, it is assumed that adjustment ratio is (Rratio, Gratio, Bratio), then, by (Rratio, Gratio,
Bratio) carry out product with each pixel of colour of skin view data, obtain R(0,1,2,...,n), G(0,1,2,..,.n),
B(0,1,2,...,n), wherein n is integer.
Statistics R (0,1,2 ... n), G (0,1,2 ... n), B (0,1,2 ... maximum RGB in n)maxAs target picture
Element color value.
Sub-step S1224, uses described color to adjust ratio and described object pixel color value calculates normalization coefficient.
In implementing, the ratio between default color threshold and object pixel color value can be calculated, as picture
Element color-ratio, calculates color and adjusts the product between ratio and pixel color ratio, it is thus achieved that normalization coefficient.
As a example by RGB color, it is assumed that adjustment ratio is (Rratio, Gratio, Bratio), object pixel color value is
RGBmax, then normalization coefficient is:
Rratio*255/RGBmax
Gratio*255/RGBmax
Bratio*255/RGBmax
Sub-step S123, is adjusted with described normalization coefficient on the basis of described original colour of skin color value, it is thus achieved that
Normalization colour of skin color value;
Sub-step S124, adjusts described colour of skin view data with described normalization colour of skin color value.
In embodiments of the present invention, can be adjusted according to normalization coefficient on the basis of original colour of skin color value,
Output normalization colour of skin color value.
As a example by RGB color, it is assumed that original colour of skin color value is (Rinput, Ginput, Binput), normalization coefficient be
(Rratio*255/RGBmax, Gratio*255/RGBmax, Bratio*255/RGBmax), then the normalization colour of skin color value exported
(Rfinal, Gfinal, Bfinal) it is:
Rfinal=Rinput*Rratio*255/RGBmax;
Gfinal=Ginput*Gratio*255/RGBmax;
Bfinal=Binput*Bratio*255/RGBmax;
At present, in the camera module of mobile terminal, can AEC (Automatic Exposure Control, automatically
Spectrum assignment) and AWB (Automatic white balance, AWB) stable after, indexed by the exposure of AEC
(index) value, and the color temperature value (CCT) of AWB output, remove the color rendition (color that dynamic calculation current scene should use
And saturation (color enhancement) parameter correction).
The most just create problem, such as, in different angles, different exposures, and different AWB output, even if AWB
Difference little, the color rendition of final utilization and saturation parameters can be inconsistent, and the image colour of skin causing out is inconsistent,
Even same person is tested, in different angles, in the case of different light sources, colour of skin difference is the biggest.
Meanwhile, the screen of the mobile terminal of different-colour (warm colour screen, cool colour screen etc.) shows that form is each especially
Different.
Therefore, Consumer's Experience is the most bad, the most existing adjustable parameter, and adjustment method, and debugging cycle is the longest, and
And it is extremely difficult to expected effect.
The scheme that the present invention provides, user can use mobile terminal, according to target colour of skin color value to colour of skin picture number
According to being normalized so that the colour of skin of input can tend to, be even up to the target colour of skin, solves the colour of skin by image procossing
Control, stability in the large is poor, causes the colour of skin under circumstances, shows different problem, the colour of skin that output is stable, consistent,
Meanwhile, the debugging cycle of image procossing is shortened.
With reference to Fig. 2, it is shown that the processing method embodiment of another kind of according to an embodiment of the invention view data
Flow chart of steps, specifically may include steps of:
Step 201, obtains the raw image data that photographic head gathers when preview.
Step 202, carries out image procossing to described raw image data.
In embodiments of the present invention, if camera collection is to view data, then can carry out ISP (Image Signal
Processing, image signal processing) process.
Wherein, image procossing includes following at least one:
1, auto-exposure control
Exposure is used to calculate the physical quantity of the luminous flux size arriving camera from scenery.Imageing sensor is only just obtaining
True exposure, just can obtain high-quality photo.Over-exposed, image seems the brightest under-exposure, then image seems too
Secretly.The size of the luminous flux arriving sensor is mainly determined by two aspect factors: the length of time of exposure and the size of aperture.
Utilize aperture to carry out automatic exposure, mainly control aperture size according to captured scene so that light-inletting quantity is tieed up
Hold within the specific limits.The cost being exposed controlling by aperture is higher.
Auto-exposure control algorithmic method generally has two kinds:
A kind of method is to use with reference to brightness value, and image uniform is divided into the subimage of many, each piece of subimage bright
Degree is used to arrange with reference to brightness value, and this brightness value can be obtained by the speed arranging shutter.
Another method is, is exposed by the relation between brightness and the exposure value under research different illumination conditions
Photocontrol.
2, blank level adjustment
White balance is it can be appreciated that under the conditions of any colour temperature, the reference white captured by photographic head is through the tune of oversampling circuit
Whole, remain as white after being allowed to imaging.
AWB be based on the assumption that the meansigma methods of the color of scene fall specific at one in the range of, if measured
Deviateing this scope to result, then adjust corresponding parameter, correction is until its average falls into appointment scope.This processing procedure is potentially based on
Yuv space, it is also possible to carry out based on rgb space.For Sensor, common processing mode is to be increased by correction R/B
Benefit so that UV value falls in the range of an appointment.Thus realize AWB.
3, color rendition processes
The human eye identification to color, is, based on human eye, light is existed three kinds of different sensing units, different sensing lists
There is the principle of different response curves in unit to the light of different-waveband, is obtained the perception of color by the synthesis of brain.In general,
The concept by RGB three primary colours that can be popular understands decomposition and the synthesis of color.
In theory, if human eye and the sensor (sensor) response to the coloured light of spectrum, if embodiment spectrally,
The substantially response to three coloured light, will not make a difference each other, does not has so-called cross effect.But, practical situation is also
The most preferable, the trichroism induction system of the human eye response condition to spectrum, is that the response of RGB is not completely self-contained.
On each component of RGB the most devious to the response of spectrum with human eye, be certainly accomplished by it is corrected.
The most just in cross effect, the response intensity of each to color equally component is also required to correction, it is common practice to by one
Color is once corrected by color correction matrix.
The computing of this colour correction is typically integrated by sensor module or rear end ISP and completes, and posts by amendment is relevant
Storage obtains correct correction result.Wherein, also it is the conversion by a 3*3 due to color space conversion from RGB to YUV
Matrix realizes, so sometimes the two matrix can combine during ISP processes, is transported by a matrix
Calculate and operated the correction of color and the conversion of color space.
4, color enhancement processes
In implementing, the color representation of view data can be strengthened by modes such as regulation saturations.
So-called saturation, refer to is the purity of color in fact, and purity is the highest, shows the distinctest, and purity is relatively low, and performance is then
Dulller.
Owing to each pixel of liquid crystal is made up of red, green, blue (RGB) subpixel, backlight by rely on after liquid crystal molecule RGB as
Element is combined into random color light.If RGB three primary colors is the most bright-coloured, then the color gamut that display can represent is the widest.As
Really display three primary colors is the most bright-coloured, and the color gamut that this display can show is the most narrow, because it cannot show ratio
Three primary colors more chromatic colour.Therefore, the method improving color saturation is to improve backlight spectra and trichromatic purity.
5, denoising
In the collection and transmission of view data, image data quality be often subject to various effect of noise and under
Fall.
Such as, the sound pollution when imageing sensor obtains view data, owing to data volume at this time is less, noise
Directly affect interpolation algorithm below, and make the details of image to embody, both affected the interpolation of image, also affected people's
Visual experience.
Therefore in image procossing, the removal of noise is a very important link.
The mode of denoising, it is common that the point of surrounding taking average to substitute original value, this way does not increase
Quantity of information, is similar to a fuzzy algorithmic approach.
When detection, comprehensively can judge noise as standard by brightness and color, use interpolation algorithm to compensate,
For the bad point that sensor is intrinsic, noise, the mode of shielding is used to abandon its data etc..
Certainly, above-mentioned image procossing is intended only as example, when implementing the embodiment of the present invention, can set according to practical situation
Putting other image procossing, as stroboscopic suppresses, this is not any limitation as by the embodiment of the present invention.It addition, in addition to above-mentioned image procossing,
Those skilled in the art can also use other image procossing according to actual needs, and this is not limited by the embodiment of the present invention
System.
Step 203, identifies the first volumetric image data in described raw image data.
Step 204, obtains the Image Processing parameter arranged when processing for the second human body image data.
Step 205, processes described the first volumetric image data according to described Image Processing parameter, it is thus achieved that target figure
As data.
In embodiments of the present invention, can be from raw image data identification the first human body picture number after image procossing
According to, obtain the Image Processing parameter arranged when processing for the second human body image data, according to Image Processing parameter to figure
As the first volumetric image data after processing processes, it is thus achieved that destination image data.
For embodiment of the method, in order to be briefly described, therefore it is all expressed as a series of combination of actions, but this area
Technical staff should know, the embodiment of the present invention is not limited by described sequence of movement, because implementing according to the present invention
Example, some step can use other orders or carry out simultaneously.Secondly, those skilled in the art also should know, description
Described in embodiment belong to preferred embodiment, necessary to the involved action not necessarily embodiment of the present invention.
With reference to Fig. 3, it is shown that the knot of the processing means embodiment of a kind of view data
Structure block diagram, specifically can include such as lower module:
Raw image data acquisition module 301, for obtaining the raw image data of camera collection;
Human body image data identification module 302, for identifying the first human body picture number in described raw image data
According to;
Image Processing parameter acquisition module 303, is arranged when processing for the second human body image data for obtaining
Image Processing parameter;
Human body image data processing module 304, is used for according to described Image Processing parameter described first human body picture number
According to processing, it is thus achieved that destination image data.
In one embodiment of the invention, described Image Processing parameter includes target colour of skin color value;
Described human body image data processing module 304 can be also used for:
Colour of skin view data is identified from described the first volumetric image data;
According to described target colour of skin color value, described colour of skin view data is normalized.
In one embodiment of the invention, described human body image data processing module 304 can be also used for:
Eigen Skin color view data is selected in described colour of skin view data;
According to described target colour of skin color value, described Eigen Skin color view data is normalized.
In one embodiment of the invention, described human body image data processing module 304 can be also used for:
Add up brightness and/or the exposure of described colour of skin view data;
From described colour of skin view data, choose brightness be less than, in default brightness section and/or exposure, the exposure preset
The view data of threshold value, as Eigen Skin color view data.
In one embodiment of the invention, described human body image data processing module 304 can be also used for:
Add up the original colour of skin color value in described colour of skin view data;
Described original colour of skin color value is used to calculate normalization coefficient with described target colour of skin color value;
It is adjusted with described normalization coefficient on the basis of described original colour of skin color value, it is thus achieved that normalization colour of skin face
Colour;
Described colour of skin view data is adjusted with described normalization colour of skin color value.
In one embodiment of the invention, described human body image data processing module 304 can be also used for:
Obtain the pixel color value of each pixel in described colour of skin view data;
Calculate the meansigma methods of described pixel color value, as original colour of skin color value.
In one embodiment of the invention, described human body image data processing module 304 can be also used for:
Calculate the ratio between described target colour of skin color value and described original colour of skin color value, it is thus achieved that color adjusts ratio
Example;
The pixel color value of each pixel in described colour of skin view data is multiplied by described adjustment ratio, it is thus achieved that pixel color
Value set;
Object pixel color value is chosen from described pixel color value set;
Use described color to adjust ratio and described object pixel color value calculates normalization coefficient.
In one embodiment of the invention, described human body image data processing module 304 can be also used for:
From described pixel color value set, the pixel color value that selected value is maximum, as object pixel color value.
In one embodiment of the invention, described human body image data processing module 304 can be also used for:
Calculate the ratio between color threshold and the described object pixel color value preset, as pixel color ratio;
Calculate described color and adjust the product between ratio and described pixel color ratio, it is thus achieved that normalization coefficient.
With reference to Fig. 4, it is shown that the processing means embodiment of another kind of according to an embodiment of the invention view data
Structured flowchart, specifically can include such as lower module:
Raw image data acquisition module 401, for obtaining the raw image data of camera collection;
Image processing module 402, for carrying out image procossing to described raw image data;
Human body image data identification module 403, for identifying the first human body picture number in described raw image data
According to;
Image Processing parameter acquisition module 404, is arranged when processing for the second human body image data for obtaining
Image Processing parameter;
Human body image data processing module 405, is used for according to described Image Processing parameter described first human body picture number
According to processing, it is thus achieved that destination image data.
In implementing, described image procossing can include following at least one:
Auto-exposure control, blank level adjustment, color rendition process, color enhancement process, denoising.
For device embodiment, due to itself and embodiment of the method basic simlarity, so describe is fairly simple, relevant
Part sees the part of embodiment of the method and illustrates.
The embodiment of the present invention additionally provides mobile terminal, as it is shown in figure 5, for convenience of description, illustrate only and the present invention
The part that embodiment is relevant, concrete ins and outs do not disclose, and refer to embodiment of the present invention method part.This terminal can be
Including mobile phone, panel computer, PDA (Personal Digital Assistant, personal digital assistant), POS (Point of
Sales, point-of-sale terminal), the arbitrarily terminal unit such as vehicle-mounted computer, as a example by terminal is as mobile phone:
Fig. 5 is illustrated that the block diagram of the part-structure of the mobile phone relevant to the terminal of embodiment of the present invention offer.With reference to figure
5, mobile phone includes: radio frequency (Radio Frequency, RF) circuit 510, memorizer 520, input block 530, display unit 540,
Sensor 550, voicefrequency circuit 560, Wireless Fidelity (wireless fidelity, WiFi) module 570, processor 580 and
Power supply 590 parts such as grade.It will be understood by those skilled in the art that the handset structure shown in Fig. 5 is not intended that the restriction to mobile phone,
Can include that ratio illustrates more or less of parts, or combine some parts, or different parts are arranged.
Below in conjunction with Fig. 5 each component parts of mobile phone carried out concrete introduction:
RF circuit 510 can be used for receiving and sending messages or in communication process, the reception of signal and transmission, especially, by base station
After downlink information receives, process to processor 580;It addition, be sent to base station by designing up data.Generally, RF circuit 510
Include but not limited to antenna, at least one amplifier, transceiver, bonder, low-noise amplifier (Low Noise
Amplifier, LNA), duplexer etc..Additionally, RF circuit 510 can also be communicated with network and other equipment by radio communication.
Above-mentioned radio communication can use arbitrary communication standard or agreement, includes but not limited to global system for mobile communications (Global
System of Mobile communication, GSM), general packet radio service (General Packet Radio
Service, GPRS), CDMA (Code Division Multiple Access, CDMA), WCDMA
(Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution,
LTE), Email, Short Message Service (Short Messaging Service, SMS) etc..
Memorizer 520 can be used for storing software program and module, and processor 580 is stored in memorizer 520 by operation
Software program and module, thus perform mobile phone various functions application and data process.Memorizer 520 can mainly include
Storage program area and storage data field, wherein, storage program area can store the application journey needed for operating system, at least one function
Sequence (such as sound-playing function, image player function etc.) etc.;Storage data field can store what the use according to mobile phone was created
Data (such as voice data, phone directory etc.) etc..Additionally, memorizer 520 can include high-speed random access memory, it is also possible to
Including nonvolatile memory, for example, at least one disk memory, flush memory device or other volatile solid-state
Part.
Input block 530 can be used for receiving numeral or the character information of input, and produce with the user setup of mobile phone with
And function controls relevant key signals input.Specifically, input block 530 can include that contact panel 531 and other inputs set
Standby 532.Contact panel 531, also referred to as touch screen, can collect user thereon or neighbouring touch operation (such as user uses
Any applicable object such as finger, stylus or adnexa operation on contact panel 531 or near contact panel 531), and root
Corresponding attachment means is driven according to formula set in advance.Optionally, contact panel 531 can include touch detecting apparatus and touch
Two parts of controller.Wherein, the touch orientation of touch detecting apparatus detection user, and detect the signal that touch operation brings,
Transmit a signal to touch controller;Touch controller receives touch information from touch detecting apparatus, and is converted into touching
Point coordinates, then give processor 580, and order that processor 580 sends can be received and performed.Furthermore, it is possible to use electricity
The polytypes such as resistive, condenser type, infrared ray and surface acoustic wave realize contact panel 531.Except contact panel 531, input
Unit 530 can also include other input equipments 532.Specifically, other input equipments 532 can include but not limited to secondary or physical bond
One or more in dish, function key (such as volume control button, switch key etc.), trace ball, mouse, action bars etc..
Display unit 540 can be used for the various of the information that inputted by user of display or the information being supplied to user and mobile phone
Menu.Display unit 540 can include display floater 541, optionally, can use liquid crystal display (Liquid Crystal
Display, LCD), the form such as Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) configure aobvious
Show panel 541.Further, contact panel 531 can cover display floater 541, when contact panel 531 detects thereon or attached
After near touch operation, send processor 580 to determine the type of touch event, with preprocessor 580 according to touch event
Type corresponding visual output is provided on display floater 541.Although in Figure 5, contact panel 531 and display floater 541
It is to realize input and the input function of mobile phone as two independent parts, but in some embodiments it is possible to by touch-control
Panel 531 is integrated with display floater 541 and realizes input and the output function of mobile phone.
Mobile phone may also include at least one sensor 550, such as optical sensor, motion sensor and other sensors.
Specifically, optical sensor can include ambient light sensor and proximity transducer, and wherein, ambient light sensor can be according to ambient light
Light and shade regulate the brightness of display floater 541, proximity transducer can cut out display floater 541 when mobile phone moves in one's ear
And/or backlight.As the one of motion sensor, accelerometer sensor can detect (generally three axles) acceleration in all directions
Size, can detect that size and the direction of gravity time static, can be used for identify mobile phone attitude application (such as horizontal/vertical screen is cut
Change, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, percussion) etc.;Also may be used as mobile phone
Other sensors such as the gyroscope of configuration, barometer, drimeter, thermometer, infrared ray sensor, do not repeat them here.
Voicefrequency circuit 560, speaker 561, microphone 562 can provide the audio interface between user and mobile phone.Audio-frequency electric
The signal of telecommunication after the voice data conversion that road 560 can will receive, is transferred to speaker 561, speaker 561 is converted to sound
Signal exports;On the other hand, the acoustical signal of collection is converted to the signal of telecommunication by microphone 562, voicefrequency circuit 560 turn after receiving
It is changed to voice data, then after voice data output processor 580 is processed, through RF circuit 510 to be sent to such as another mobile phone,
Or voice data is exported to memorizer 520 to process further.
WiFi belongs to short range wireless transmission technology, and mobile phone can help user's transceiver electronics postal by WiFi module 570
Part, browsing webpage and access streaming video etc., it has provided the user wireless broadband internet and has accessed.Although Fig. 5 shows
WiFi module 570, but it is understood that, it is also not belonging to must be configured into of mobile phone, can not change as required completely
Omit in the scope of the essence becoming invention.
Processor 580 is the control centre of mobile phone, utilizes various interface and the various piece of the whole mobile phone of connection, logical
Cross operation or perform to be stored in the software program in memorizer 520 and/or module, and calling and be stored in memorizer 520
Data, perform the various functions of mobile phone and process data, thus mobile phone is carried out integral monitoring.Optionally, processor 580 can wrap
Include one or more processing unit;Preferably, processor 580 can integrated application processor and modem processor, wherein, should
Mainly process operating system, user interface and application program etc. with processor, modem processor mainly processes radio communication.
It is understood that above-mentioned modem processor can not also be integrated in processor 580.
Mobile phone also includes the power supply 590 (such as battery) powered to all parts, it is preferred that power supply can pass through power supply pipe
Reason system is logically contiguous with processor 580, thus realizes management charging, electric discharge and power managed by power-supply management system
Etc. function.
Although not shown, mobile phone can also include photographic head, bluetooth module etc., does not repeats them here.
In embodiments of the present invention, the processor 580 included by this terminal also has a following functions:
Obtain the raw image data of camera collection;
The first volumetric image data is identified in described raw image data;
Obtain the Image Processing parameter arranged when processing for the second human body image data;
According to described Image Processing parameter, described the first volumetric image data is processed, it is thus achieved that destination image data.
Alternatively, described Image Processing parameter includes target colour of skin color value;Processor 580 included by this terminal also has
There is a following functions:
Colour of skin view data is identified from described the first volumetric image data;
According to described target colour of skin color value, described colour of skin view data is normalized.
Alternatively, the processor 580 included by this terminal also has a following functions:
Eigen Skin color view data is selected in described colour of skin view data;
According to described target colour of skin color value, described Eigen Skin color view data is normalized.
Alternatively, the processor 580 included by this terminal also has a following functions:
Add up brightness and/or the exposure of described colour of skin view data;
From described colour of skin view data, choose brightness be less than, in default brightness section and/or exposure, the exposure preset
The view data of threshold value, as Eigen Skin color view data.
Alternatively, the processor 580 included by this terminal also has a following functions:
Add up the original colour of skin color value in described colour of skin view data;
Described original colour of skin color value is used to calculate normalization coefficient with described target colour of skin color value;
It is adjusted with described normalization coefficient on the basis of described original colour of skin color value, it is thus achieved that normalization colour of skin face
Colour;
Described colour of skin view data is adjusted with described normalization colour of skin color value.
Alternatively, the processor 580 included by this terminal also has a following functions:
Obtain the pixel color value of each pixel in described colour of skin view data;
Calculate the meansigma methods of described pixel color value, as original colour of skin color value.
Alternatively, the processor 580 included by this terminal also has a following functions:
Calculate the ratio between described target colour of skin color value and described original colour of skin color value, it is thus achieved that color adjusts ratio
Example;
The pixel color value of each pixel in described colour of skin view data is multiplied by described adjustment ratio, it is thus achieved that pixel color
Value set;
Object pixel color value is chosen from described pixel color value set;
Use described color to adjust ratio and described object pixel color value calculates normalization coefficient.
Alternatively, the processor 580 included by this terminal also has a following functions:
From described pixel color value set, the pixel color value that selected value is maximum, as object pixel color value.
Alternatively, the processor 580 included by this terminal also has a following functions:
Calculate the ratio between color threshold and the described object pixel color value preset, as pixel color ratio;
Calculate described color and adjust the product between ratio and described pixel color ratio, it is thus achieved that normalization coefficient.
Alternatively, the processor 580 included by this terminal also has a following functions:
Described raw image data is carried out image procossing;
Wherein, described image procossing includes following at least one:
Auto-exposure control, blank level adjustment, color rendition process, color enhancement process, denoising.
Those skilled in the art is it can be understood that arrive, for convenience and simplicity of description, and the system of foregoing description,
The specific works process of device and unit, is referred to the corresponding process in preceding method embodiment, does not repeats them here.
In several embodiments provided by the present invention, it should be understood that disclosed system, apparatus and method are permissible
Realize by another way.Such as, device embodiment described above is only schematically, such as, and described unit
Dividing, be only a kind of logic function and divide, actual can have other dividing mode, the most multiple unit or assembly when realizing
Can in conjunction with or be desirably integrated into another system, or some features can be ignored, or does not performs.Another point, shown or
The coupling each other discussed or direct-coupling or communication connection can be the indirect couplings by some interfaces, device or unit
Close or communication connection, can be electrical, machinery or other form.
The described unit illustrated as separating component can be or may not be physically separate, shows as unit
The parts shown can be or may not be physical location, i.e. may be located at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected according to the actual needs to realize the mesh of the present embodiment scheme
's.
It addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, it is also possible to two or more unit are integrated in a unit.Above-mentioned integrated list
Unit both can realize to use the form of hardware, it would however also be possible to employ the form of SFU software functional unit realizes.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
Completing instructing relevant hardware by program, this program can be stored in a computer-readable recording medium, storage
Medium may include that read only memory (ROM, Read Only Memory), random access memory (RAM, Random
Access Memory), disk or CD etc..
One of ordinary skill in the art will appreciate that all or part of step realizing in above-described embodiment method is permissible
Instructing relevant hardware by program to complete, described program can be stored in a kind of computer-readable recording medium, on
Stating the storage medium mentioned can be read only memory, disk or CD etc..
Above a kind of mobile terminal provided by the present invention is described in detail, for the general technology people of this area
Member, according to the thought of the embodiment of the present invention, the most all will change, in sum,
This specification content should not be construed as limitation of the present invention.
The embodiment of the invention discloses A1, the processing method of a kind of view data, including: obtain the original of camera collection
View data;The first volumetric image data is identified in described raw image data;Obtain for the second human body image data
The Image Processing parameter arranged when processing;According to described Image Processing parameter to described the first volumetric image data at
Reason, it is thus achieved that destination image data.A2, method as described in A1, described Image Processing parameter includes target colour of skin color value;Described
Include according to the step that described the first volumetric image data is processed by described Image Processing parameter: from described first human figure
As data identify colour of skin view data;According to described target colour of skin color value, described colour of skin view data is normalized place
Reason.A3, method as described in A2, described be normalized place according to described target colour of skin color value to described colour of skin view data
The step of reason includes: select Eigen Skin color view data in described colour of skin view data;According to described target colour of skin color value
Described Eigen Skin color view data is normalized.A4, method as described in A3, described in described colour of skin view data
The step of middle selection Eigen Skin color view data includes: add up brightness and/or the exposure of described colour of skin view data;From described
Colour of skin view data is chosen brightness and is less than the picture number of the threshold exposure preset in default brightness section and/or exposure
According to, as Eigen Skin color view data.A5, method as described in A2 or A3 or A4, described according to described target colour of skin color value
The step being normalized described colour of skin view data includes: add up the original colour of skin face in described colour of skin view data
Colour;Described original colour of skin color value is used to calculate normalization coefficient with described target colour of skin color value;In the described original colour of skin
It is adjusted with described normalization coefficient on the basis of color value, it is thus achieved that normalization colour of skin color value;With the described normalization colour of skin
Color value adjusts described colour of skin view data.A6, method as described in A5, original in described statistics described colour of skin view data
The step of colour of skin color value includes: obtain the pixel color value of each pixel in described colour of skin view data;Calculate described pixel
The meansigma methods of color value, as original colour of skin color value.A7, method as described in A5, the described original colour of skin color of described employing
The step that value calculates normalization coefficient with described target colour of skin color value includes: calculate described target colour of skin color value former with described
Ratio between beginning colour of skin color value, it is thus achieved that color adjusts ratio;By the pixel face of each pixel in described colour of skin view data
Colour is multiplied by described adjustment ratio, it is thus achieved that pixel color value set;Object pixel face is chosen from described pixel color value set
Colour;Use described color to adjust ratio and described object pixel color value calculates normalization coefficient.A8, side as described in A7
Method, the described step choosing object pixel color value from described pixel color value set includes: from described pixel color value collection
In conjunction, the pixel color value that selected value is maximum, as object pixel color value.A9, method as described in A7, described in described employing
Color adjusts ratio and described object pixel color value and calculates the step of normalization coefficient and include: calculate the color threshold preset with
Ratio between described object pixel color value, as pixel color ratio;Calculate described color and adjust ratio and described pixel
Product between color-ratio, it is thus achieved that normalization coefficient.A10, method as described in any one of A1-A9, described described former
Before identifying the step of the first volumetric image data in beginning view data, described method also includes: to described original image number
According to carrying out image procossing;Wherein, described image procossing includes following at least one: auto-exposure control, blank level adjustment, color
Color reduction treatment, color enhancement process, denoising.
The embodiment of the invention also discloses B11, the processing means of a kind of view data, including: raw image data obtains
Module, for obtaining the raw image data of camera collection;Human body image data identification module, at described original image
Data identify the first volumetric image data;Image Processing parameter acquisition module, for obtaining for the second human body image number
According to the Image Processing parameter arranged when processing;Human body image data processing module, for according to described Image Processing parameter
Described the first volumetric image data is processed, it is thus achieved that destination image data.B12, device as described in B11, described image
Processing parameter includes target colour of skin color value;Described human body image data processing module is additionally operable to: from described first human body image
Data identify colour of skin view data;According to described target colour of skin color value, described colour of skin view data is normalized place
Reason.B13, device as described in B12, described human body image data processing module is additionally operable to: select in described colour of skin view data
Select Eigen Skin color view data;According to described target colour of skin color value, described Eigen Skin color view data is normalized place
Reason.B14, device as described in B13, described human body image data processing module is additionally operable to: add up described colour of skin view data
Brightness and/or exposure;From described colour of skin view data, choose brightness be less than pre-in default brightness section and/or exposure
If the view data of threshold exposure, as Eigen Skin color view data.B15, device as described in B12 or B13 or B14, institute
State human body image data processing module to be additionally operable to: the original colour of skin color value adding up in described colour of skin view data;Use described
Original colour of skin color value calculates normalization coefficient with described target colour of skin color value;On the basis of described original colour of skin color value
It is adjusted with described normalization coefficient, it is thus achieved that normalization colour of skin color value;Adjust described with described normalization colour of skin color value
Colour of skin view data.B16, device as described in B15, described human body image data processing module is additionally operable to: obtain the described colour of skin
The pixel color value of each pixel in view data;Calculate the meansigma methods of described pixel color value, as original colour of skin color value.
B17, device as described in B15, described human body image data processing module is additionally operable to: calculate described target colour of skin color value and institute
State the ratio between original colour of skin color value, it is thus achieved that color adjusts ratio;By the picture of each pixel in described colour of skin view data
Element color value is multiplied by described adjustment ratio, it is thus achieved that pixel color value set;Target picture is chosen from described pixel color value set
Element color value;Use described color to adjust ratio and described object pixel color value calculates normalization coefficient.B18, as described in B17
Device, described human body image data processing module is additionally operable to: from described pixel color value set, the pixel that selected value is maximum
Color value, as object pixel color value.B19, device as described in B17, described human body image data processing module is additionally operable to:
Calculate the ratio between color threshold and the described object pixel color value preset, as pixel color ratio;Calculate described face
Product between the whole ratio of tone and described pixel color ratio, it is thus achieved that normalization coefficient.B20, as described in any one of B11-B19
Device, also include: image processing module, for described raw image data is carried out image procossing;Wherein, at described image
Reason includes following at least one: at auto-exposure control, blank level adjustment, color rendition process, color enhancement process, denoising
Reason.
The embodiment of the invention also discloses C21, a kind of mobile terminal, including: memorizer and processor;Wherein, deposit described in
Reservoir, for storing the instruction of the raw image data obtaining camera collection, identifies first in described raw image data
The instruction of human body image data, obtains the finger of the Image Processing parameter arranged when processing for the second human body image data
Order, processes described the first volumetric image data according to described Image Processing parameter, it is thus achieved that destination image data instructs;Institute
State processor for: according to the instruction of the raw image data of described acquisition camera collection, obtain the original of camera collection
View data;In described raw image data, the instruction of the first volumetric image data is identified, in described original graph according to described
As data identify the first volumetric image data;Arrange when processing for the second human body image data according to described acquisition
The instruction of Image Processing parameter, obtain the Image Processing parameter arranged when processing for the second human body image data;Depend on
Described the first volumetric image data is processed according to described Image Processing parameter according to described, it is thus achieved that the finger of destination image data
Order, processes described the first volumetric image data according to described Image Processing parameter, it is thus achieved that destination image data.C22, as
Mobile terminal described in C21, described Image Processing parameter includes target colour of skin color value;Described processor is additionally operable to: from described
The first volumetric image data identifies colour of skin view data;According to described target colour of skin color value, described colour of skin view data is entered
Row normalized.C23, mobile terminal as described in C22, described processor is additionally operable to: select in described colour of skin view data
Select Eigen Skin color view data;According to described target colour of skin color value, described Eigen Skin color view data is normalized place
Reason.C24, mobile terminal as described in C23, described processor is additionally operable to: add up brightness and/or the exposure of described colour of skin view data
Luminosity;From described colour of skin view data, choose brightness be less than, in default brightness section and/or exposure, the threshold exposure preset
The view data of value, as Eigen Skin color view data.C25, mobile terminal as described in C22 or C23 or C24, described process
Device is additionally operable to: add up the original colour of skin color value in described colour of skin view data;Use described original colour of skin color value with described
Target colour of skin color value calculates normalization coefficient;Carry out with described normalization coefficient on the basis of described original colour of skin color value
Adjust, it is thus achieved that normalization colour of skin color value;Described colour of skin view data is adjusted with described normalization colour of skin color value.C26, as
Mobile terminal described in C25, described processor is additionally operable to: obtain the pixel color of each pixel in described colour of skin view data
Value;Calculate the meansigma methods of described pixel color value, as original colour of skin color value.C27, mobile terminal as described in C25, described
Processor is additionally operable to: calculate the ratio between described target colour of skin color value and described original colour of skin color value, it is thus achieved that color is adjusted
Whole ratio;The pixel color value of each pixel in described colour of skin view data is multiplied by described adjustment ratio, it is thus achieved that pixel color
Value set;Object pixel color value is chosen from described pixel color value set;Described color is used to adjust ratio and described mesh
Mark pixel color value calculates normalization coefficient.C28, mobile terminal as described in C27, described processor is additionally operable to: from described picture
In element color value set, the pixel color value that selected value is maximum, as object pixel color value.C29, movement as described in C27
Terminal, described processor is additionally operable to: calculate the ratio between color threshold and the described object pixel color value preset, as picture
Element color-ratio;Calculate described color and adjust the product between ratio and described pixel color ratio, it is thus achieved that normalization coefficient.
C30, mobile terminal as described in any one of C21-C29, described memorizer is additionally operable to storage to be carried out described raw image data
The instruction of image procossing;Described processor is additionally operable to: according to the described instruction that described raw image data carries out image procossing,
Described raw image data is carried out image procossing;Wherein, described image procossing includes following at least one: automatic exposure control
System, blank level adjustment, color rendition process, color enhancement process, denoising.
Claims (10)
1. a processing method for view data, including:
Obtain the raw image data of camera collection;
The first volumetric image data is identified in described raw image data;
Obtain the Image Processing parameter arranged when processing for the second human body image data;
According to described Image Processing parameter, described the first volumetric image data is processed, it is thus achieved that destination image data.
2. the method for claim 1, it is characterised in that described Image Processing parameter includes target colour of skin color value;
The described step processed described the first volumetric image data according to described Image Processing parameter includes:
Colour of skin view data is identified from described the first volumetric image data;
According to described target colour of skin color value, described colour of skin view data is normalized.
3. method as claimed in claim 2, it is characterised in that described according to described target colour of skin color value to described broca scale
The step being normalized as data includes:
Eigen Skin color view data is selected in described colour of skin view data;
According to described target colour of skin color value, described Eigen Skin color view data is normalized.
4. method as claimed in claim 3, it is characterised in that described selection Eigen Skin color figure in described colour of skin view data
As the step of data includes:
Add up brightness and/or the exposure of described colour of skin view data;
From described colour of skin view data, choose brightness be less than, in default brightness section and/or exposure, the threshold exposure preset
View data, as Eigen Skin color view data.
5. the method as described in Claims 2 or 3 or 4, it is characterised in that described according to described target colour of skin color value to described
The step that colour of skin view data is normalized includes:
Add up the original colour of skin color value in described colour of skin view data;
Described original colour of skin color value is used to calculate normalization coefficient with described target colour of skin color value;
It is adjusted with described normalization coefficient on the basis of described original colour of skin color value, it is thus achieved that normalization colour of skin color
Value;
Described colour of skin view data is adjusted with described normalization colour of skin color value.
6. method as claimed in claim 5, it is characterised in that the original colour of skin face in described statistics described colour of skin view data
The step of colour includes:
Obtain the pixel color value of each pixel in described colour of skin view data;
Calculate the meansigma methods of described pixel color value, as original colour of skin color value.
7. method as claimed in claim 5, it is characterised in that the described original colour of skin color value of described employing and described target skin
Color color value calculates the step of normalization coefficient and includes:
Calculate the ratio between described target colour of skin color value and described original colour of skin color value, it is thus achieved that color adjusts ratio;
The pixel color value of each pixel in described colour of skin view data is multiplied by described adjustment ratio, it is thus achieved that pixel color value collection
Close;
Object pixel color value is chosen from described pixel color value set;
Use described color to adjust ratio and described object pixel color value calculates normalization coefficient.
8. method as claimed in claim 7, it is characterised in that described choose object pixel from described pixel color value set
The step of color value includes:
From described pixel color value set, the pixel color value that selected value is maximum, as object pixel color value.
9. a processing means for view data, including:
Raw image data acquisition module, for obtaining the raw image data of camera collection;
Human body image data identification module, for identifying the first volumetric image data in described raw image data;
Image Processing parameter acquisition module, the image procossing arranged when processing for the second human body image data for obtaining
Parameter;
Human body image data processing module, at according to described Image Processing parameter to described the first volumetric image data
Reason, it is thus achieved that destination image data.
10. a mobile terminal, including:
Memorizer and processor;
Wherein, described memorizer is for storing the instruction of the raw image data obtaining camera collection, at described original image
Data identify the instruction of the first volumetric image data, obtains the figure arranged when processing for the second human body image data
As the instruction of processing parameter, according to described Image Processing parameter, described the first volumetric image data is processed, it is thus achieved that target
View data instructs;
Described processor is used for:
According to the instruction of the raw image data of described acquisition camera collection, obtain the raw image data of camera collection;
In described raw image data, the instruction of the first volumetric image data is identified, at described raw image data according to described
In identify the first volumetric image data;
The instruction of the Image Processing parameter arranged when processing for the second human body image data according to described acquisition, obtains pin
The Image Processing parameter arranged when second human body image data is processed;
Described the first volumetric image data is processed according to described Image Processing parameter according to described, it is thus achieved that target image number
According to instruction, according to described Image Processing parameter, described the first volumetric image data is processed, it is thus achieved that destination image data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610530720.8A CN106210517A (en) | 2016-07-06 | 2016-07-06 | The processing method of a kind of view data, device and mobile terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610530720.8A CN106210517A (en) | 2016-07-06 | 2016-07-06 | The processing method of a kind of view data, device and mobile terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106210517A true CN106210517A (en) | 2016-12-07 |
Family
ID=57473762
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610530720.8A Pending CN106210517A (en) | 2016-07-06 | 2016-07-06 | The processing method of a kind of view data, device and mobile terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106210517A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106657793A (en) * | 2017-01-11 | 2017-05-10 | 维沃移动通信有限公司 | Image processing method and mobile terminal |
CN106952235A (en) * | 2017-02-10 | 2017-07-14 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
CN108848306A (en) * | 2018-06-25 | 2018-11-20 | Oppo广东移动通信有限公司 | Image processing method and device, electronic equipment, computer readable storage medium |
CN108961192A (en) * | 2018-07-19 | 2018-12-07 | 深圳市华星光电技术有限公司 | Enhancement Method, computer storage medium and the display device of color saturation of image |
CN109978757A (en) * | 2019-03-20 | 2019-07-05 | 维沃移动通信有限公司 | A kind of image processing method and terminal device |
CN110533651A (en) * | 2019-08-29 | 2019-12-03 | 维沃移动通信有限公司 | A kind of image processing method and device |
CN114013372A (en) * | 2021-10-19 | 2022-02-08 | 深圳市美通视讯科技有限公司 | Automobile electronic exterior rearview mirror system and control method |
CN114040108A (en) * | 2021-11-19 | 2022-02-11 | 杭州逗酷软件科技有限公司 | Auxiliary shooting method, device, terminal and computer readable storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070258656A1 (en) * | 2006-05-05 | 2007-11-08 | Parham Aarabi | Method, system and computer program product for automatic and semi-automatic modification of digital images of faces |
CN101964874A (en) * | 2009-07-23 | 2011-02-02 | 卡西欧计算机株式会社 | Image processing apparatus and image processing method |
CN102916984A (en) * | 2011-08-01 | 2013-02-06 | 腾讯科技(深圳)有限公司 | Picture editing action sharing method and system |
CN104284055A (en) * | 2013-07-01 | 2015-01-14 | 索尼公司 | Image processing method, device and electronic equipment thereof |
CN104751408A (en) * | 2015-03-26 | 2015-07-01 | 广东欧珀移动通信有限公司 | Face image adjusting method and device |
CN104796683A (en) * | 2014-01-22 | 2015-07-22 | 中兴通讯股份有限公司 | Image color calibration method and system |
CN105204850A (en) * | 2015-08-31 | 2015-12-30 | 深圳市金立通信设备有限公司 | Image processing method and terminal |
CN105530435A (en) * | 2016-02-01 | 2016-04-27 | 深圳市金立通信设备有限公司 | Shooting method and mobile terminal |
-
2016
- 2016-07-06 CN CN201610530720.8A patent/CN106210517A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070258656A1 (en) * | 2006-05-05 | 2007-11-08 | Parham Aarabi | Method, system and computer program product for automatic and semi-automatic modification of digital images of faces |
CN101964874A (en) * | 2009-07-23 | 2011-02-02 | 卡西欧计算机株式会社 | Image processing apparatus and image processing method |
CN102916984A (en) * | 2011-08-01 | 2013-02-06 | 腾讯科技(深圳)有限公司 | Picture editing action sharing method and system |
CN104284055A (en) * | 2013-07-01 | 2015-01-14 | 索尼公司 | Image processing method, device and electronic equipment thereof |
CN104796683A (en) * | 2014-01-22 | 2015-07-22 | 中兴通讯股份有限公司 | Image color calibration method and system |
CN104751408A (en) * | 2015-03-26 | 2015-07-01 | 广东欧珀移动通信有限公司 | Face image adjusting method and device |
CN105204850A (en) * | 2015-08-31 | 2015-12-30 | 深圳市金立通信设备有限公司 | Image processing method and terminal |
CN105530435A (en) * | 2016-02-01 | 2016-04-27 | 深圳市金立通信设备有限公司 | Shooting method and mobile terminal |
Non-Patent Citations (1)
Title |
---|
赵明华等: "基于肤色分割、数学形态学和几何方法的人脸检测", 《四川大学学报(自然科学版)》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106657793A (en) * | 2017-01-11 | 2017-05-10 | 维沃移动通信有限公司 | Image processing method and mobile terminal |
CN106657793B (en) * | 2017-01-11 | 2019-01-22 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
CN106952235B (en) * | 2017-02-10 | 2019-07-26 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
CN106952235A (en) * | 2017-02-10 | 2017-07-14 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
CN108848306A (en) * | 2018-06-25 | 2018-11-20 | Oppo广东移动通信有限公司 | Image processing method and device, electronic equipment, computer readable storage medium |
CN108961192A (en) * | 2018-07-19 | 2018-12-07 | 深圳市华星光电技术有限公司 | Enhancement Method, computer storage medium and the display device of color saturation of image |
CN108961192B (en) * | 2018-07-19 | 2021-06-29 | Tcl华星光电技术有限公司 | Image color saturation enhancement method, computer storage medium and display device |
CN109978757A (en) * | 2019-03-20 | 2019-07-05 | 维沃移动通信有限公司 | A kind of image processing method and terminal device |
CN109978757B (en) * | 2019-03-20 | 2023-08-22 | 维沃移动通信有限公司 | Image processing method and terminal equipment |
CN110533651A (en) * | 2019-08-29 | 2019-12-03 | 维沃移动通信有限公司 | A kind of image processing method and device |
CN114013372A (en) * | 2021-10-19 | 2022-02-08 | 深圳市美通视讯科技有限公司 | Automobile electronic exterior rearview mirror system and control method |
CN114040108A (en) * | 2021-11-19 | 2022-02-11 | 杭州逗酷软件科技有限公司 | Auxiliary shooting method, device, terminal and computer readable storage medium |
WO2023087929A1 (en) * | 2021-11-19 | 2023-05-25 | 杭州逗酷软件科技有限公司 | Assisted photographing method and apparatus, and terminal and computer-readable storage medium |
CN114040108B (en) * | 2021-11-19 | 2023-12-01 | 杭州逗酷软件科技有限公司 | Auxiliary shooting method, device, terminal and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106101547A (en) | The processing method of a kind of view data, device and mobile terminal | |
CN106096588A (en) | The processing method of a kind of view data, device and mobile terminal | |
CN106210517A (en) | The processing method of a kind of view data, device and mobile terminal | |
CN108307125B (en) | Image acquisition method, device and storage medium | |
CN109547701B (en) | Image shooting method and device, storage medium and electronic equipment | |
CN106060402A (en) | Image data processing method and device, and mobile terminal | |
CN107862265B (en) | Image processing method and related product | |
CN107423699B (en) | Biopsy method and Related product | |
US11430209B2 (en) | Image signal processing method, apparatus, and device | |
US10949958B2 (en) | Fast fourier color constancy | |
CN109191410A (en) | A kind of facial image fusion method, device and storage medium | |
CN109272459A (en) | Image processing method, device, storage medium and electronic equipment | |
CN111885304B (en) | Photographing method, mobile terminal and computer storage medium | |
CN105872373B (en) | A kind of automatic defogging photographic method, device and equipment | |
CN105809647A (en) | Automatic defogging photographing method, device and equipment | |
CN108510955A (en) | Adjust the method and Related product of brightness of display screen | |
CN107613191A (en) | A kind of photographic method, equipment and computer-readable recording medium | |
CN104869320A (en) | Electronic device and control method of the same | |
CN107302663A (en) | A kind of brightness of image method of adjustment, terminal and computer-readable recording medium | |
CN106134189B (en) | Image processing apparatus, photographic device, image processing method and program | |
CN106797453A (en) | Image processing apparatus, camera head, image processing method and image processing program | |
CN107451979A (en) | A kind of image processing method, device and storage medium | |
CN109729281A (en) | Image processing method, device, storage medium and terminal | |
CN108711402A (en) | Brightness of display screen method of adjustment and Related product | |
CN104735362A (en) | Picture taking method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |
|
RJ01 | Rejection of invention patent application after publication |